Denumerable continuous-time Markov decision processes with multiconstraints on average costs.
Qiuli LiuHangSheng TanXianping GuoPublished in: Int. J. Syst. Sci. (2012)
Keyphrases
- markov decision processes
- average cost
- state space
- stationary policies
- optimal control
- finite state
- optimal policy
- transition matrices
- infinite horizon
- policy iteration
- finite horizon
- discounted reward
- reachability analysis
- long run
- reinforcement learning
- markov chain
- dynamic programming
- risk sensitive
- total cost
- factored mdps
- initial state
- action sets
- reward function
- partially observable
- markov decision process
- decision theoretic planning
- average reward
- reinforcement learning algorithms
- partially observable markov decision processes
- planning under uncertainty
- markov decision problems
- state and action spaces
- multistage
- model based reinforcement learning
- machine learning
- data mining
- function approximation
- planning problems
- linear program
- dynamical systems
- heuristic search
- search space
- semi markov decision processes